Abstract
In this paper, we propose a variance-based subgradient extragradient algorithm with line search for stochastic variational inequality problems by aiming at robustness with respect to an unknown Lipschitz constant. This algorithm may be regarded as an integration of a subgradient extragradient algorithm for deterministic variational inequality problems and a stochastic approximation method for expected values. At each iteration, different from the conventional variance-based extragradient algorithms to take projection onto the feasible set twicely, our algorithm conducts a subgradient projection which can be calculated explicitly. Since our algorithm requires only one projection at each iteration, the computation load may be reduced. We discuss the asymptotic convergence, the sublinear convergence rate in terms of the mean natural residual function, and the optimal oracle complexity for the proposed algorithm. Furthermore, we establish the linear convergence rate with finite computational budget under both the strongly Minty variational inequality and the error bound condition. Preliminary numerical experiments indicate that the proposed algorithm is competitive with some existing methods.
Similar content being viewed by others
Data Availability Statement
The datasets generated during the current study are available from the corresponding author on reasonable request.
References
Burkholder, D.L., Davis, B.J., Gundy, R.F.: Integral inequalities for convex functions of operators on martingales. Presented at the (1972)
Cai, X., Gu, G., He, B.: On the \(O(1/t)\) convergence rate of the projection and contraction methods for variational inequalities with Lipschitz continuous monotone operators. Comput. Optim. Appl. 57(2), 339–363 (2014)
Censor, Y., Gibali, A., Reich, S.: Extensions of Korpelevich’s extragradient method for the variational inequality problem in Euclidean space. Optimization 61(9), 1119–1132 (2012)
Censor, Y., Gibali, A., Reich, S.: Strong convergence of subgradient extragradient methods for the variational inequality problem in Hilbert space. Optim. Method. Soft. 26(4–5), 827–845 (2011)
Censor, Y., Gibali, A., Reich, S.: The subgradient extragradient method for solving variational inequalities in Hilbert space. J. Optim. Theory Appl. 148(2), 318–335 (2011)
Chen, Y., Lan, G., Ouyang, Y.: Accelerated schemes for a class of variational inequalities. Math. Program. 165(1), 113–149 (2017)
Chen, X., Sun, H., Xu, H.: Discrete approximation of two-stage stochastic and distributionally robust linear complementarity. Math. Program. 177(1), 255–289 (2019)
Cui, S., Shanbhag, U.V.: On the analysis of reflected gradient and splitting methods for monotone stochastic variational inequality problems. Presented at the (2016)
Dang, C.D., Lan, G.: On the convergence properties of non-Euclidean extragradient methods for variational inequalities with generalized monotone operators. Comput. Optim. Appl. 60(2), 277–310 (2015)
Facchinei, F., Pang, J.S.: Finite-Dimensional Variational Inequalities and Complementarity Problems. I and II. Springer, New York (2003)
Fukushima, M.: Equivalent differentiable optimization problems and descent methods for asymmetric variational inequality problems. Math. Program. 53(1), 99–110 (1992)
Gürkan, G., Yonca, Özge A., Robonson, S.M.: Sample-path solution of stochastic variational inequalities. Math. Program. 84(2), 313–333 (1999)
Iusem, A.N., Jofré, A., Oliveira, R.I., Thompson, P.: Extragradient method with variance reduction for stochastic variational inequalities. SIAM J. Optimiz. 27(2), 686–724 (2017)
Iusem, A.N., Jofré, A., Oliveira, R.I., Thompson, P.: Variance-based extragradient methods with line search for stochastic variational inequalities. SIAM J. Optimiz. 29(1), 175–206 (2019)
Iusem, A.N., Jofré, A., Thompson, P.: Incremental constraint projection methods for monotone stochastic variational inequalities. Math. Oper. Res. 44(1), 236–263 (2019)
Jadamba, B., Raciti, F.: Variational inequality approach to stochastic Nash equilibrium problems with an application to Cournot oligopoly. J. Optim. Theory Appl. 165(3), 1050–1070 (2015)
Jalilzadeh, A., Shanbhag, U.V., eg-VSSA, : An extragradient variable sample-size stochastic approximation scheme: error analysis and complexity trade-offs. Presented at the (2016)
Jiang, J., Chen, X., Chen, Z.: Quantitative analysis for a class of two-stage stochastic linear variational inequality problems. Comput. Optim. Appl. 76(2), 431–460 (2020)
Jiang, H., Xu, H.: Stochastic approximation approaches to the stochastic variational inequality problem. IEEE T. Automat. Control 53(6), 1462–1475 (2008)
Kannan, A., Shanbhag, U.V.: Distributed computation of equilibria in monotone Nash games via iterative regularization techniques. SIAM J. Optimiz. 22(4), 1177–1205 (2012)
Kannan, A., Shanbhag, U.V.: Optimal stochastic extragradient schemes for pseudomonotone stochastic variational inequality problems and their variants. Comput. Optim. Appl. 74(3), 779–820 (2019)
Koshal, J., Nediéc, A., Shanbhag, U.V.: Distributed algorithms for aggregative games on graphs. Oper. Res. 64(3), 680–704 (2016)
Koshal, J., Nedić, A., Shanbhag, U.V.: Regularized iterative stochastic approximation methods for stochastic variational inequality problems. IEEE T. Automat. Control 58(3), 594–609 (2013)
Lei, J., Shanbhag, U.V.: Linearly convergent variable sample-size schemes for stochastic Nash games: Best-response schemes and distributed gradient-response schemes. Presented at the (2018)
Lin, G.H., Fukushima, M.: Stochastic equilibrium problems and stochastic mathematical programs with equilibrium constraints: A survey. Pac. J. Optim. 6(3), 455–482 (2010)
Liu, M., Mroueh, Y., Ross, J., Zhang, W., Cui, X., Das, P., Yang, T.: Towards better understanding of adaptive gradient algorithms in generative adversarial nets. In: Proceedings of the 2020 International Conference on Learning Representations, (2020). https://openreview.net/forum?id=SJxIm0VtwH
Mertikopoulos, P., Zhou, Z.: Learning in games with continuous action sets and unknown payoff functions. Math. Program. 173(1), 465–507 (2019)
Mertikopoulos, P., Lecouat, B., Zenati, H., Foo, C.S., Chandrasekhar, V., Piliouras, G.: In: Optimistic Mirror Descent in Saddle-point Problems: Going the Extra (gradient) Mile, pp. 1–23. United States, New Orleans (2019)
Ravat, U., Shanbhag, U.V.: On the characterization of solution sets of smooth and nonsmooth convex stochastic Nash games. SIAM J. Optimiz. 21(3), 1168–1199 (2011)
Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22, 400–407 (1951)
Robbins H., Siegund D.: A convergence theorem for non-negative almost supermartingales and some applications, In: Optimizing Methods in Statistics (Proceedings of a Symposium at Ohio State University, Columbus, Ohio), Rustagi, J. S. (eds.), Academic Press, New York, pp. 233-257 (1971)
Shanbhag, U.V.: Stochastic variational inequality problems: Applications, analysis, and algorithms. Inf. Tutorials Oper. Res. pp. 71–107,(2013)
Shanbhag, U.V., Blanchet, J.H.: In: Budget-constrained Stochastic Approximation, pp. 368–379. , Huntington Beach, CA (2015)
Shapiro, A., Dentcheva, D., Ruszczynski, A.: Lectures on Stochastic Programming: Modeling and Theory. SIAM, Philadelphia (2009)
Solodov, M.V., Svaiter, B.F.: A new projection method for variational inequality problems. SIAM J. Control Optim. 37(3), 765–776 (1999)
Sun, H., Chen, X.: Two-stage stochastic variational inequalities: Theory, algorithms and applications. J. Oper. Res. Soc. China 9, 1–32 (2021)
Wang, M., Lin, G.H., Gao, Y., Ali, M.M.: Sample average approximation method for a class of stochastic variational inequality problems. J. Syst. Sci. Complex. 24(6), 1143–1153 (2011)
Xu, H.: Sample average approximation methods for a class of stochastic variational inequality problems. Asia Pac. J. Oper. Res. 27(1), 103–119 (2010)
Yang, Z.P., Wang, Y., Lin, G.H.: Variance-based modified backward-forward algorithm with line search for stochastic variational inequality problems and its applications. Asia Pac. J. Oper. Res. 37(3), 1–33 (2020)
Yang, Z.P., Zhang, J., Zhu, X., Lin, G.H.: Infeasible interior-point algorithms based on sampling average approximations for a class of stochastic complementarity problems and their applications. J. Comput. Appl. Math. 352, 382–400 (2019)
Ye J.J., Yuan X., Zeng S., Zhang J.: Variational analysis perspective on linear convergence of some first order methods for nonsmooth convex optimization problems. Set-Valued Var. Anal. doi: https://doi.org/10.1007/s11228-021-00591-3(2021)
Yousefian, F., Nedić, A., Shanbhag, U.V.: On smoothing, regularization, and averaging in stochastic approximation methods for stochastic variational inequality problems. Math. Program. 165(1), 391–431 (2017)
Yousefian, F., Nedić, A., Shanbhag, U.V.: On stochastic mirror-prox algorithms for stochastic Cartesian variational inequalities randomized block coordinate and optimal averaging schemes. Set-Valued Var. Anal. 26(4), 789–819 (2018)
Yousefian, F., Nedić, A., Shanbhag, U.V.: In: Optimal Robust Smoothing Extragradient Algorithms for Stochastic Variational Inequality Problems, pp. 5831–5836. , Los Angeles, CA (2014)
Yousefian, F., Nedić, A., Shanbhag, U.V.: Self-tuned stochastic approximation schemes for non-Lipschitzian stochastic multi-user optimization and Nash games. IEEE T. Automat. Control 61(7), 1753–1766 (2016)
Yu, C., Van Der Schaar, M., Sayed, A.H.: Distributed learning for stochastic generalized Nash equilibrium problems. IEEE T. Signal Proces. 65(15), 3893–3908 (2017)
Zhang, X.J., Du, X.W., Yang, Z.P., Lin, G.H.: An infeasible stochastic approximation and projection algorithm for stochastic variational inequalities. J. Optim. Theory Appl. 183(3), 1053–1076 (2019)
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work was supported in part by NSFC (Nos. 12071280, 11971220), Shenzhen Science and Technology Program (No. RCYX20200714114700072), Stable Support Plan Program of Shenzhen Natural Science Fund (No. 20200925152128002), Guangdong Basic and Applied Basic Research Foundation (No. 2019A1515011152), the Young Talents in Higher Education of Guangdong (No. 2020KQNCX079), and the Open Project of Key Laboratory of School of Mathematical Sciences of Chongqing Normal University (No. CSSXKFKTZ202001).
Appendices
Appendix A: Proof of Lemma 4.3
First of all, we use Lemma 2.6 with \(p=q\), \(x^k\in \mathcal{F}_k\) and noting that \(\xi ^k\) is independent of \(\mathcal{F}_k\), we have
Applying Lemma 2.6 again with \(p=q\), \(y^k\in \mathcal{F}_k\) and noting that \(\eta ^k\) is independent of \(\mathcal{F}_k\) and \(\Big |\big |\cdot |\widehat{\mathcal{F}}_k\big |_p|\mathcal{F}_k\Big |_p=|\cdot |\mathcal{F}_k|\), we have
From Lemma 2.7, Assumption 4.2 and noting that \(0<\alpha _k\le \widehat{\alpha }\le 1\), \(y^k=y(x^k,\alpha _k,\xi ^k)\), \(x^k\in \mathcal{F}_k\), \(\xi ^k\) is independent of \(\mathcal{F}_k\), we have
On the other hand, putting together Step 3 in Algorithm 1, Lemmas 2.1 and 2.3, we obtain
Taking \(|\cdot |\mathcal{F}_k|_p\) in the above inequality, we have
Putting together relations (A.1)–(A.4) and use the facts that \(\big |a^2\big |\mathcal{F}_k\big |_{\frac{p}{2}}=\big |a\big |\mathcal{F}_k\big |_p^2,\ (a+b)^2\le 2a^2+2b^2,\ \widehat{L}_{2p}>L_pC_p,\ c_1>C_p\) and \(\sigma _{2p}(x^*)\ge \sigma _p(x^*)\), the claim with \(\mathcal{C}_p:=2c_1^2\left( 7-3\lambda ^2+\sup _k\frac{12L_p^2\widehat{\alpha }^2C_p^2}{N_k}\right) \) and \(\overline{\mathcal{C}}_p:=2\left( 4-3\lambda ^2+6(1+\widehat{\alpha } L)^2+\sup _k\frac{12L_p^2\widehat{\alpha }^2C_p^2}{N_k}\right) \) is proved. \(\square \)
1.1 Appendix B: Proof of Lemma 4.4
By \(y^k\in \widehat{\mathcal{F}}_k\) and \(\eta ^k\) is independent of \(\widehat{\mathcal{F}}_k\), we have
Taking \(\mathbb {E}[\cdot |\mathcal {F}_k]\) in (4.1), we can get the conclusion from Lemmas 4.1 and 4.3 immediately.
Appendix C: Proof of Theorem 4.1
By Lemma 4.4, we have
Taking into account \(\sum _kN_k^{-1}<\infty \). By applying Lemma 2.4 with \(v^k:=\Vert x^k-x^*\Vert ^2,\ a_k:=\frac{\overline{\mathcal{C}}_2\widehat{\alpha }^2\widehat{L}^2_4}{N_k},\ b_k:=\frac{\mathcal{C}_2\widehat{\alpha }^2\sigma _4^2(x^*)}{N_k}\), and \(u_k:=\frac{(1-3\lambda ^2)(\min \{\lambda \theta ,\widehat{\alpha }\})^2}{2|\mathrm {L}(\xi )|^2_2}\mathfrak {R}^2(F,x^k)\), we have that, almost surely, \(\{\Vert x^k-x^*\Vert ^2\}\) converges and \(\sum _{k=0}^{\infty }\mathfrak {R}^2(F,x^k)<\infty \). In particular, almost surely, \(\{x^k\}\) is bounded and \(0=\lim _{k\rightarrow \infty }\mathfrak {R}^2(F,x^k)=\lim _{k\rightarrow \infty }\Vert x^k-\Pi _X[x^k-F(x^k)]\Vert ^2\). This fact and the continuity of F and \(\Pi _X\) almost surely imply that every cluster point \(\bar{x}\) of \(\{x^k\}\) satisfies \(\Vert \bar{x}-\Pi _X[\bar{x}-F(\bar{x})]\Vert ^2=0\). Then, we conclude from Lemma 2.1 that \(\bar{x}\in X^*\). This together with the boundedness of \(\{x^k\}\) and the fact that every cluster point of \(\{x^k\}\) belonging to \(X^*\) indicate that \(\lim _{k\rightarrow \infty }\mathrm{d}(x^k,X^*)=0\) almost surely. In a similar way, we can deduce that \(\lim _{k\rightarrow \infty }\mathbb {E}[\mathfrak {R}^2(F,x^k)]=0\) by taking expectation in (4.11). \(\square \)
Appendix D: Proof of Lemma 4.5
First of all, it follows from Assumption 4.2 that there must exist \(k_0\) satisfying (4.12). In the following, we let \(d_i:=\Vert x^i-x^*\Vert ^2\) for \(i\in \mathbb {N}_0\) and \(k\ge k_0\) be given. Taking expectation in (4.11), making use of \(\mathbb {E}[\mathbb {E}[\cdot \big |\widehat{\mathcal{F}}_i]]=\mathbb {E}[\cdot ]\), and drop the negative term in the right-hand side. We then sum recursively the obtained inequality from \(i:=k_0\) to \(i:=k-1\), we obtain
For any \(\varpi >0\), we define the stopping time \(t_{\varpi }:=\{k\ge k_0:|d_k|_2>\varpi \}\). From (4.12) and (A.5), we have that, for any \(\varpi >0\) such that \(t_{\varpi }<\infty \),
By the definition of \(t_{\varpi }\) for any \(\varpi >0\), the argument above implies that any threshold \(\varpi ^2\), which \(\{\big |d_k\big |^2_2\}_{k\ge k_0}\) eventually exceeds, is bounded above by \(\frac{|d_{k_0}|^2_2+\frac{\phi \mathcal{C}_2\sigma _4^2(x^*)}{\overline{\mathcal{C}}_2\widehat{L}_4^2}}{1-\phi }\). As a result, \(\{|d_k|^2_2\}_{k\ge k_0}\) is bounded and satisfies the statement of the lemma. \(\square \)
Appendix E: Proof of Theorem 4.2
Since \(\{N_k\}\) satisfies Assumption 4.2, the conclusions in Theorem 4.1 and Lemma 4.5 hold. In particular, \(\{x^k\}\) is bounded in \(\mathcal{L}^2\). Let M satisfies that \(\sup _{k\ge 0}\big |\Vert x^k-x^*\Vert \big |_2^2\le M\). Hence, we have \(\sup _k\mathbb {E}[\Vert x^k-x^*\Vert ^2]\le M\). In the recursion of Lemma 4.2, we take expectation, use \(\mathbb {E}[\mathbb {E}[\cdot \big |\widehat{\mathcal{F}}_i]]=\mathbb {E}[\cdot ]\), and summing recursively from \(i:=0\) to \(i:=k\), we have
Taking the above inequality, the bound
and \(\min _{i=0,\cdots ,k}\mathbb {E}[[\mathfrak {R}(F,x^i)^2]\le \frac{1}{k+1}\sum _{i=0}^k\mathbb {E}[[\mathfrak {R}(F,x^i)^2]\), we obtain the conclusion immediately. \(\square \)
Appendix F: Proof of Theorem 4.3
First, it follows from Theorem 4.2 that there exists a constant \(\mathcal{M}>0\) such that, for every \(k\in \mathbb {N}\),
Hence, given \(\tau >0\), we obtain \(\min _{i=0,\cdots ,K}\mathbb {E}[[\mathfrak {R}(F,x^i)^2]\le \tau \) after \(K=\mathcal{O}(nN^{-1}b^{-1}\tau ^{-1})\) iterations. The total number of oracle calls after K iterations is upper bounded by
and \(\min _{i=0,\cdots ,K}\mathbb {E}[[\mathfrak {R}(F,x^i)^2]\le \tau \). By Lemma 4.1, one can obtain that \(l_k\le \log _{\frac{1}{\theta }}\left( \frac{\widehat{\alpha }\overline{L}_k}{\min \{\lambda \theta ,\widehat{\alpha }\}}\right) \). This fact, (A.6) and \(N=\mathcal{O}(n)\) imply the claimed bound on \(\sum _{i=0}^K(1+l_i)N_i\).
The concavity of the mapping \(z\mapsto \log _{\frac{1}{\theta }}(z)\) and the Jensen’s inequality imply
where the last inequality follows from \(\mathbb {E}[\overline{L}_k]=L\) by the definitions of \(\overline{L}_k\), L and Assumption 4.2. Taking expectation in (A.6), making use of the above relation, and the fact that \(N=\mathcal{O}(n)\), implies the claimed bound on \(\sum _{i=0}^K(1+\mathbb {E}[l_i])N_i\). \(\square \)
Rights and permissions
About this article
Cite this article
Yang, ZP., Zhang, J., Wang, Y. et al. Variance-Based Subgradient Extragradient Method for Stochastic Variational Inequality Problems. J Sci Comput 89, 4 (2021). https://doi.org/10.1007/s10915-021-01603-y
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10915-021-01603-y
Keywords
- Stochastic variational inequality
- Stochastic approximation
- Subgradient extragradient algorithm
- Variance reduction
- Bounded proximal error bound
- Convergence rate